Distance Guided Generative Adversarial Network for Explainable Binary Classifications
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2023
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866916076492685312 |
|---|---|
| author | Xiong, Xiangyu Sun, Yue Liu, Xiaohong Ke, Wei Lam, Chan-Tong Chen, Jiangang Jiang, Mingfeng Wang, Mingwei Xie, Hui Tong, Tong Gao, Qinquan Chen, Hao Tan, Tao |
| author_facet | Xiong, Xiangyu Sun, Yue Liu, Xiaohong Ke, Wei Lam, Chan-Tong Chen, Jiangang Jiang, Mingfeng Wang, Mingwei Xie, Hui Tong, Tong Gao, Qinquan Chen, Hao Tan, Tao |
| contents | Despite the potential benefits of data augmentation for mitigating the data insufficiency, traditional augmentation methods primarily rely on the prior intra-domain knowledge. On the other hand, advanced generative adversarial networks (GANs) generate inter-domain samples with limited variety. These previous methods make limited contributions to describing the decision boundaries for binary classification. In this paper, we propose a distance guided GAN (DisGAN) which controls the variation degrees of generated samples in the hyperplane space. Specifically, we instantiate the idea of DisGAN by combining two ways. The first way is vertical distance GAN (VerDisGAN) where the inter-domain generation is conditioned on the vertical distances. The second way is horizontal distance GAN (HorDisGAN) where the intra-domain generation is conditioned on the horizontal distances. Furthermore, VerDisGAN can produce the class-specific regions by mapping the source images to the hyperplane. Experimental results show that DisGAN consistently outperforms the GAN-based augmentation methods with explainable binary classification. The proposed method can apply to different classification architectures and has potential to extend to multi-class classification. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2312_17538 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Distance Guided Generative Adversarial Network for Explainable Binary Classifications Xiong, Xiangyu Sun, Yue Liu, Xiaohong Ke, Wei Lam, Chan-Tong Chen, Jiangang Jiang, Mingfeng Wang, Mingwei Xie, Hui Tong, Tong Gao, Qinquan Chen, Hao Tan, Tao Computer Vision and Pattern Recognition Machine Learning Image and Video Processing Despite the potential benefits of data augmentation for mitigating the data insufficiency, traditional augmentation methods primarily rely on the prior intra-domain knowledge. On the other hand, advanced generative adversarial networks (GANs) generate inter-domain samples with limited variety. These previous methods make limited contributions to describing the decision boundaries for binary classification. In this paper, we propose a distance guided GAN (DisGAN) which controls the variation degrees of generated samples in the hyperplane space. Specifically, we instantiate the idea of DisGAN by combining two ways. The first way is vertical distance GAN (VerDisGAN) where the inter-domain generation is conditioned on the vertical distances. The second way is horizontal distance GAN (HorDisGAN) where the intra-domain generation is conditioned on the horizontal distances. Furthermore, VerDisGAN can produce the class-specific regions by mapping the source images to the hyperplane. Experimental results show that DisGAN consistently outperforms the GAN-based augmentation methods with explainable binary classification. The proposed method can apply to different classification architectures and has potential to extend to multi-class classification. |
| title | Distance Guided Generative Adversarial Network for Explainable Binary Classifications |
| topic | Computer Vision and Pattern Recognition Machine Learning Image and Video Processing |
| url | https://arxiv.org/abs/2312.17538 |